arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.05533cs.LGstat.ML
收藏

鲁棒离线深度强化学习模型偏差的克服

Overcoming Model Bias for Robust Offline Deep Reinforcement Learning

Siemens Corporate Technology(西门子企业技术);Technical University of Munich(慕尼黑工业大学)

Phillip Swazinna, Steffen Udluft, Thomas Runkler

摘要:

最先进的强化学习算法主要依赖于被允许与其环境直接交互以收集数百万个观察结果。这使得他们很难将成功转移到工业控制问题上,因为模拟通常非常昂贵或不存在,并且在真实环境中探索可能会导致灾难性事件。最近开发的无模型离线RL算法可以通过减轻价值函数中的外推误差来从单个数据集(包含有限的探索)中学习。然而,训练过程的鲁棒性仍然相对较低,这是使用价值函数的方法中已知的问题。为了提高学习过程的鲁棒性和稳定性,我们使用动态模型来评估策略性能,而不是价值函数,从而产生MOOSE(基于模型的离线策略搜索与集成),该算法通过将策略保持在数据的支持范围内来确保低模型偏差。我们将MOOSE与最先进的无模型离线RL算法{ BRAC,} BEAR和BCQ在工业基准和MuJoCo连续控制任务中的鲁棒性能进行比较,发现MOOSE在几乎所有考虑的情况下都优于其无模型同行,甚至远远超过。

英文摘要:

State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations. This makes it hard to transfer their success to industrial control problems, where simulations are often very costly or do not exist, and exploring in the real environment can potentially lead to catastrophic events. Recently developed, model-free, offline RL algorithms, can learn from a single dataset (containing limited exploration) by mitigating extrapolation error in value functions. However, the robustness of the training process is still comparatively low, a problem known from methods using value functions. To improve robustness and stability of the learning process, we use dynamics models to assess policy performance instead of value functions, resulting in MOOSE (MOdel-based Offline policy Search with Ensembles), an algorithm which ensures low model bias by keeping the policy within the support of the data. We compare MOOSE with state-of-the-art model-free, offline RL algorithms { BRAC,} BEAR and BCQ on the Industrial Benchmark and MuJoCo continuous control tasks in terms of robust performance, and find that MOOSE outperforms its model-free counterparts in almost all considered cases, often even by far.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑